Presents Lens Privacy Sealing as a pre-sensor hardware privacy method, introduces the P3AR dataset with privacy annotations, and proposes MSPNet with IFNS and CFSA modules that nearly double action recognition accuracy on degraded videos while keeping identity recognition low.
Learning transferable visual models from natural language supervision
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
WATCH localizes archaeological site changes to the month using temporal embedding distances and self-supervised signals on PlanetScope data, with TED achieving 55% exact-month recall and 92.5% within three months on Afghan sites.
citing papers explorer
-
Lens Privacy Sealing: A New Benchmark and Method for Physical Privacy-Preserving Action Recognition
Presents Lens Privacy Sealing as a pre-sensor hardware privacy method, introduces the P3AR dataset with privacy annotations, and proposes MSPNet with IFNS and CFSA modules that nearly double action recognition accuracy on degraded videos while keeping identity recognition low.
-
WATCH: Wide-Area Archaeological Site Tracking for Change Detection
WATCH localizes archaeological site changes to the month using temporal embedding distances and self-supervised signals on PlanetScope data, with TED achieving 55% exact-month recall and 92.5% within three months on Afghan sites.